Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Sep 11, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

493

High dynamic range image reconstruction based on efficient multi-scale attention.

GuoWei Xiang, BenDu Bai

    Applied Optics
    |August 12, 2025
    PubMed
    Summary
    This summary is machine-generated.

    Related Concept Videos

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    Development of a novel high-performance portable barrier based on full-scale field tests and simulation optimization.

    Scientific reports·2025
    Same author

    Image fusion via nonlocal sparse K-SVD dictionary learning.

    Applied optics·2016
    Same author

    Object tracking based on incremental Bi-2DPCA learning with sparse structure.

    Applied optics·2015
    Same journal

    Multifunctional reconfigurable terahertz metasurface based on vanadium dioxide phase transition: achieving broadband absorption and efficient polarization conversion.

    Applied optics·2026
    Same journal

    High-Q-factor electromagnetically induced transparency utilizing quasi-bound states in the continuum in an all-dielectric terahertz metasurface.

    Applied optics·2026
    Same journal

    Automated stitching interferometry for high-precision metrology of X-ray mirrors.

    Applied optics·2026
    Same journal

    Experimental demonstration of an approach to designing a metal-dielectric DBR resonant cavity structure.

    Applied optics·2026
    Same journal

    High-precision wavefront reconstruction from a single-shot interferogram using a physics-driven hybrid feature calibration network.

    Applied optics·2026
    Same journal

    Ultra-high-Q Fano resonance based on coupled topological corner states in Kagome photonic crystals.

    Applied optics·2026
    See all related articles

    This study introduces an efficient hybrid transformer network for high dynamic range (HDR) image reconstruction, effectively reducing ghosting artifacts and improving computational speed for clearer images.

    Area of Science:

    • Computer Vision
    • Image Processing
    • Artificial Intelligence

    Background:

    • Ghosting artifacts from motion and complex transformers hinder high dynamic range (HDR) image reconstruction.
    • Existing methods struggle with computational complexity and artifact reduction.

    Purpose of the Study:

    • To develop an efficient HDR image reconstruction network.
    • To address ghosting artifacts and computational challenges in HDR imaging.

    Main Methods:

    • Proposed an HDR reconstruction network with a hybrid perception transformer.
    • Integrated efficient multi-scale attention mechanisms, including spatial attention for cross-exposure fusion.
    • Utilized an efficient context extractor and window attention for enhanced global-local feature interaction.

    More Related Videos

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    635

    Related Experiment Videos

    Last Updated: Sep 11, 2025

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    493
    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    635

    Main Results:

    • The network effectively preserves texture features from images with varying exposures.
    • Successfully reduced information interference in over- and under-saturated regions.
    • Achieved favorable reconstruction performance with significantly improved computational efficiency.

    Conclusions:

    • The proposed hybrid transformer network offers an effective solution for HDR image reconstruction.
    • Demonstrates superior performance in artifact reduction and computational efficiency compared to traditional methods.